Learning Quickly to Plan Quickly Using Modular Meta-Learning

Chitnis, Rohan; Kaelbling, Leslie Pack; Lozano-Pérez, Tomás

doi:10.1109/icra.2019.8794342

Cited by 19 publications

(14 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is a body of related work on guiding the choice of continuous parameters given the abstract action sequences (Chitnis et al, 2019;Kim et al, 2018Kim et al, , 2019a. In particular, we directly build on our previous work on using GANs for learning a sampler (Kim et al, 2018(Kim et al, , 2019a, but in this work we use advanced GAN training technique that offers much more stable training (Gulrajani et al, 2017).…”

Section: Learning To Guide Planningmentioning

confidence: 99%

Representation, learning, and planning algorithms for geometric task and motion planning

Kim

Shimanuki²,

Kaelbling

et al. 2021

The International Journal of Robotics Research

Self Cite

View full text Add to dashboard Cite

We present a framework for learning to guide geometric task-and-motion planning (G-TAMP). G-TAMP is a subclass of task-and-motion planning in which the goal is to move multiple objects to target regions among movable obstacles. A standard graph search algorithm is not directly applicable, because G-TAMP problems involve hybrid search spaces and expensive action feasibility checks. To handle this, we introduce a novel planner that extends basic heuristic search with random sampling and a heuristic function that prioritizes feasibility checking on promising state–action pairs. The main drawback of such pure planners is that they lack the ability to learn from planning experience to improve their efficiency. We propose two learning algorithms to address this. The first is an algorithm for learning a rank function that guides the discrete task-level search, and the second is an algorithm for learning a sampler that guides the continuous motion-level search. We propose design principles for designing data-efficient algorithms for learning from planning experience and representations for effective generalization. We evaluate our framework in challenging G-TAMP problems, and show that we can improve both planning and data efficiency.

show abstract

Section: Learning To Guide Planningmentioning

confidence: 99%

Representation, learning, and planning algorithms for geometric task and motion planning

Kim

Shimanuki²,

Kaelbling

et al. 2021

The International Journal of Robotics Research

Self Cite

View full text Add to dashboard Cite

show abstract

“…Learning techniques have been integrated into many aspects of TAMP systems, from learning samplers for continuous values [13], [14], [15], [16] to learning guidance for symbolic planning [9], [10], [14]. The latter is our focus in this paper; we assume samplers are given, and we aim to learn operators that enable symbolic planning in TAMP.…”

Section: B Learning For Task and Motion Planningmentioning

confidence: 99%

Learning Symbolic Operators for Task and Motion Planning

Silver¹,

Chitnis²,

Tenenbaum³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Robotic planning problems in hybrid state and action spaces can be solved by integrated task and motion planners (TAMP) that handle the complex interaction between motion-level decisions and task-level plan feasibility. TAMP approaches rely on domain-specific symbolic operators to guide the task-level search, making planning efficient. In this work, we formalize and study the problem of operator learning for TAMP.Central to this study is the view that operators define a lossy abstraction of the transition model of the underlying domain.We then propose a bottom-up relational learning method for operator learning and show how the learned operators can be used for planning in a TAMP system. Experimentally, we provide results in three domains, including long-horizon robotic planning tasks. We find our approach to substantially outperform several baselines, including three graph neural network-based model-free approaches based on recent work.

show abstract

“…Moreover some studies have found that some types of modular structures emerged in standard neural networks [17,18]. New strategies have been proposed for combining the modularity of neural networks with meta learning [12,19,20], with a general trend of learning modules that can be recombined to solve new tasks, leading to better performance and combinatorial generalization.…”

Section: Related Workmentioning

confidence: 99%

Multimodal Modular Meta-Learning

Sikka¹,

Tendle²,

Kayid³

2020

Preprint

View full text Add to dashboard Cite

Many real world prediction problems involve structured tasks across multiple modalities. We propose to extend previous work in modular meta learning to the multimodal setting. Specifically, we present an algorithmic approach to apply task aware modulation to a modular meta learning system that decomposes structured multimodal problems into a set of modules that can be reassembled to learn new tasks. We also propose a series of experiments to compare this approach with state of the art modular and multimodal meta learning approaches on multimodal function prediction and image classification tasks.

show abstract

Learning Quickly to Plan Quickly Using Modular Meta-Learning

Cited by 19 publications

References 26 publications

Representation, learning, and planning algorithms for geometric task and motion planning

Representation, learning, and planning algorithms for geometric task and motion planning

Learning Symbolic Operators for Task and Motion Planning

Multimodal Modular Meta-Learning

Contact Info

Product

Resources

About